A developer has created a tool called knowledge-shelf to help the AI coding assistant Cursor remember codebase patterns and conventions across sessions. This tool functions as an MCP server, allowing Cursor to search and retrieve relevant information from a local knowledge base instead of loading all data upfront, which can consume valuable context. Knowledge-shelf supports storing various types of information, such as API patterns, code templates, and architectural decisions, and operates without embeddings or a vector database, relying instead on keyword scoring for efficiency. AI
Summary written by gemini-2.5-flash-lite from 1 sources. How we write summaries →
IMPACT Enhances the usability of AI coding assistants by improving context retention and reducing repetitive explanations.
RANK_REASON This is a user-created tool that enhances an existing AI product, rather than a release from a major AI lab or a significant industry event.